© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83967
    Prev
    Next
    INDEX
    Explanations

    percentages of population

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numerical population statistics (counts or percentages) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    闥
    -1.84
    ,$_
    -1.52
    gewä
    -1.51
     Einrichtungen
    -1.51
     so
    -1.50
    Odpovědět
    -1.49
    nimmt
    -1.45
    ၉
    -1.44
    rália
    -1.38
    毆
    -1.38
    POSITIVE LOGITS
     
    2.09
     seiner
    2.02
     ''
    1.79
    ``
    1.76
    ''
    1.72
    "
    1.70
     «
    1.67
    o
    1.67
     antes
    1.64
     ``
    1.64
    Activations Density 0.029%

    No Known Activations